Negative demonstrations: a retry that duplicated a purchase order, annotated record by record

Short answer

Negative demonstrations are recorded examples of actions that fail, kept together with the reason they fail. In an ordinary purchasing workflow, one looks like an integration that retried a timed-out order as a fresh create and sent the supplier a duplicate purchase order, followed by the ticket, the cancellation and the fix. For a referral, what matters is whether the company kept the state before the action, the action, its consequence and the written reason, and who can authorize a licensing discussion.

Visual briefFull-size diagram
A fork diagram: an approved $18,400 purchase order is sent, the response times out, and the path splits. Retrying as a new create leads to two purchase orders and $36,800 committed, marked as the negative demonstration; checking by external ID first leads to one purchase order for $18,400.
Illustrative purchase order at a fictional distributor. The failing branch is only useful as data if the records show why it failed.

What does negative demonstrations mean in an ordinary business workflow?

It means keeping a mistake on file with its explanation. A negative demonstration is the counterpart to a worked example of the right way: instead of "do this," it says "this looked reasonable, and here is what it broke."

Ordinary business systems produce these whenever someone reverses a mistake and writes down why. A canceled duplicate order, a reversed payment, a voided credit memo with a note, a rollback ticket: each one pairs a wrong action with its consequence. What turns that into a demonstration is the reason. Without it, a buyer sees only that a record was canceled, not which choice caused the problem or what the safer choice would have been.

AI developers care because software agents act through the same systems, and they meet the same traps people do. Our explainer on why AI agents fail covers the general pattern. AI data vendors also advertise this kind of work: Appen's agentic AI page, for example, lists failure-mode annotation across plan, tool use and output. That shows the category exists. It does not show that any particular company's error archive is wanted, or usable.

The duplicate purchase order, annotated (Illustrative)

This case is fictional. A 260-person industrial distributor approves a purchase order for packaging film worth $18,400. Its procurement tool sends the order to the ERP through an integration, and the ERP passes it to the supplier.

TimeWhat happenedRecord it leftWhy it matters to a reviewer
Day 1, 14:02Integration sends a create request for the approved orderIntegration run log with payload referenceThe intended state: one order, $18,400
Day 1, 14:02ERP creates PO-55120, but the response never reaches the integrationERP record with creation time; integration log shows a timeoutThe outcome is now unknown to the sender
Day 1, 14:03Integration retries as a fresh create, with no stable external referenceSecond run log; ERP creates PO-55121The failing action. This is the step a negative demonstration isolates
Day 1, 14:10Both orders go to the supplierTwo outbound order messagesThe error has left the building
Day 9Buyer sees $36,800 on the supplier statement and opens a ticketTicket with both PO numbersThe consequence, written down by a person
Day 10PO-55121 canceled after the supplier agrees; integration changed to check for an existing order firstCancellation with reason code; change ticketThe reason and the safer alternative

The annotation that makes row three useful comes from published guidance, not opinion. The HTTP standard (RFC 9110) classes POST as not idempotent and says a client should not automatically retry such a request unless it has some way to know the retry is safe. Stripe's API documentation makes the same point for payments: a server error leaves the outcome unknown, so check the object before retrying under a new key, and use an idempotency key so a retry cannot perform the operation twice. NetSuite's documentation recommends external IDs with its upsert operation specifically to prevent duplicate records. A reviewer can therefore label the retry as wrong for a stated, checkable reason.

Evidence fields that turn a mistake into a demonstration

An error on its own is just noise. The duplicate order becomes a negative demonstration only when these fields survive and can be joined.

FieldValue in the example (Illustrative)Why a reviewer needs it
Starting stateOne approved order for $18,400, not yet in the ERPShows what "correct" would have looked like
Action takenSecond create request at 14:03 with no stable external referenceIsolates the exact choice that failed
Signal available at the timeTimeout on the first request; outcome unknownShows what the actor knew when choosing
ConsequenceTwo orders sent; $36,800 committedMeasures the harm in business terms
DetectionBuyer's ticket on day 9 citing both PO numbersDates the discovery and names who found it
CorrectionPO-55121 canceled with a reason codeShows how the state was restored
Written reasonRetry should have checked for an existing order firstTurns the record from "what happened" into "why it was wrong"
Safer alternativeIntegration changed to look up by external ID before creatingPairs the failure with the right behavior

The last two rows carry most of the value. Plenty of companies have canceled duplicates. Fewer have the note that explains the cause and the change that prevented a repeat, which is what lets someone label the failing step rather than guess at it.

What this one example cannot show is how often the pattern recurs, whether every case carries a reason, or how long the integration logs were kept. Those are questions about the archive as a whole, and they are answered in SourceX's review with the company, not from a single case.

Who can open the conversation, and what stays unknown?

The company needs 50 or more full-time employees at peak (contractors excluded), documented operating history, rights to license its records, and an authorized contact. Companies in the U.S., Canada and the EU qualify, as do companies in the UK, Australia, New Zealand, India, Singapore, South Africa, Latin America, the UAE and Saudi Arabia when at least 70% of the data is in English.

The right first contact is usually the CFO or COO, because purchasing, ERP and integration records sit under them, with the CEO approving. Whether a company can license this material at all is covered in can a company license its data to AI companies, and the evidence that AI developers pay for business data is collected in AI companies pay for data.

Unknown until SourceX reviews it: how many failures pass the acceptance check, how supplier and employee details are de-identified, whether vendor contracts limit use, and whether any buyer wants this failure type. Partners never request exports, screenshots or sample transactions. Related concepts are in the data types hub.

Go deeper on negative demonstrations

Next step

Refer a company. No cap on rewards. Default reward on a company's first qualifying transaction: the greater of $50,000 plus 5% and 15% of Actual Supplier Payout, with no cap; further qualifying transactions first agreed within 12 months of the first Closing pay 15%. Eligibility and payment conditions apply, including the USD 100,000 Minimum Transaction, and a signed Schedule A or addendum can differ. A lead, meeting or signature alone does not trigger payment.

If the procurement or finance lead confirms that reversed orders carry reasons and that integration logs or tickets survive long enough to explain them, register as a partner, check the company against who qualifies, and read the terms before you introduce the CFO or COO.

  1. Step 1Share your linkSend your personal link to a company you know.
  2. Step 2Company appliesThe company applies itself at /apply.
  3. Step 3Company signs and is paidThe company signs, delivers its data and is paid by SourceX under its agreement.
  4. Step 4You get your rewardthe greater of $50,000 plus 5% and 15% of the actual supplier payout, with no cap. A reward becomes payable after SourceX has paid the referred company under its signed agreement and the payout conditions in the program terms are met, including finance approval and your tax and payment details.

Common questions

Is a negative demonstration just an error log?

No. An error log says something went wrong. A negative demonstration also records the action that caused it, the state before it, and why that action was the wrong choice, usually through a ticket or reversal that a person wrote.

Does a company need many failures to have useful records?

Not necessarily many, but the same kind of failure needs to recur often enough to show a pattern, and each case needs its outcome recorded. A handful of undocumented incidents is a weaker basis than a steady stream of reversed transactions with reasons.

Should I ask the client for an example of a failed transaction?

No. Partners stay at metadata level: which system, how many cases, how long they are kept, who owns them. SourceX reviews actual records only under an agreement with the company.

Sources

  1. rfc-editor.org/rfc/rfc9110.html
  2. docs.stripe.com/api/idempotent_requests
  3. docs.oracle.com/en/cloud/saas/netsuite/ns-online-help/sectio…
  4. appen.com/agentic-ai
  5. refer.sourcex.si/terms

Free resources

Know a company with valuable proprietary data?

Become a referral partner, get your link and introduce the company’s CEO (in an owner-run company, usually the owner). Referral partners can join from most countries. We can't work with partners in countries or regions under U.S. sanctions or on U.S. restricted-party lists. The companies you introduce should be based in the U.S., Canada and the EU, or in the UK, Australia, New Zealand, India, Singapore, South Africa, Latin America, the UAE and Saudi Arabia with at least 70% of their data in English.

Refer a company →

I own a business

Explore licensing your company's data directly to SourceX for AI training and evaluation. Start a short assessment; no uploads needed.

Start an assessment